Authors:
Darya Tarasowa
and
Sören Auer
Affiliation:
University of Leipzig, Germany
Keyword(s):
Multiple-choice Questions, Multiple-mark Questions, Scoring Methods.
Related
Ontology
Subjects/Areas/Topics:
Assessment Software Tools
;
Computer-Supported Education
;
e-Testing and Test Theories
;
Learning/Teaching Methodologies and Assessment
Abstract:
Advantages and disadvantages of a learning assessment based on multiple-choice questions (MCQs) are a long and widely discussed issue in the scientific community. However, in practice this type of questions is very popular due to the possibility of automatic evaluation and scoring. Consequently, an important research question is to exploiting the strengths and mitigate the weaknesses of MCQs. In this work we discuss one particularly important issue of MCQs, namely methods for scoring results in the case, when the MCQ has several correct alternatives (multiple-mark questions, MMQs). We propose a general approach and mathematical model to score MMQs, that aims at recognizing guessing while at the same time resulting in a balanced score. In our approach conventional MCQs are viewed as a particular case of multiple-mark questions, thus, the formulas can be applied to tests mixing MCQs and MMQs. The rational of our approach is that scoring should be based on the guessing level of the ques
tion. Our approach can be added as an option, or even as a replacement for manual penalization. We show that our scoring method outperforms existing methods and demonstrate that with synthetic and real experiments.
(More)